51616 1ec757f43a eval unpack + fw_qa_level_3 data def + fast tokenizer		2025-06-24 21:51:17 +09:00
..
data	eval unpack + fw_qa_level_3 data def + fast tokenizer	2025-06-24 21:51:17 +09:00
modeling	initial one-lora-multi-q model interface	2025-06-23 16:33:45 +09:00
__init__.py	monkey patch liger kernel for gemma-3-1b-it	2025-06-19 04:44:24 +09:00
configs.py	fixing non-packed collator + packing working and trainable	2025-06-24 17:35:50 +09:00
eval_utils.py	better string processing	2025-06-24 18:17:15 +09:00
hooks.py	rearrange + move to uv (#1)	2025-05-27 21:18:15 +09:00
metrics.py	more organized eval + viz_utils (llm-comparator)	2025-06-13 08:17:21 +00:00
model_loading.py	compile linear + loss + swtich from hook to lora_forward	2025-06-20 23:41:32 +09:00
monkey_patch.py	monkey patch liger kernel for gemma-3-1b-it	2025-06-19 04:44:24 +09:00
pooling.py	rearrange + move to uv (#1)	2025-05-27 21:18:15 +09:00
trainer.py	data exp + packing	2025-06-17 11:34:16 +00:00
utils.py	fixing non-packed collator + packing working and trainable	2025-06-24 17:35:50 +09:00
viz_utils.py	llm comparator	2025-06-17 11:35:04 +00:00